The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses npx to execute commands such as npx vigiles compile, npx vigiles lint, and npx vigiles init to generate artifacts and validate project configuration.
[EXTERNAL_DOWNLOADS]: The skill utilizes npx, which downloads packages from the npm registry if not present locally. It also references an external plugin via the /plugin install command for the vigiles toolset.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by using user-supplied $ARGUMENTS to direct the modification of executable TypeScript specification files.
Ingestion points: User input provided via the $ARGUMENTS parameter in SKILL.md is used to guide file edits in .spec.ts files.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when incorporating user input into the editing process.
Capability inventory: The skill has the ability to read and write files (specifically .spec.ts files) and execute shell commands via npx.
Sanitization: The skill does not implement specific sanitization or validation logic for the user-supplied strings before they are used to modify the project's specification code.

edit-spec